Title :
Intelligent-memory architecture for artificial neural networks
Author :
Büddefeld, Jürgen ; Grosspietsch, Karl E.
Abstract :
Execution of artificial neural networks, especially for online pattern recognition, mainly depends on time-efficient execution of weighted sums. A new architecture achieves this goal, with a computation time superior to the time complexity of sequential von Neumann machines. This architecture uses additional logic to extend the functionality of conventional RAM. The authors discuss an implementation of this architecture that uses reconfigurable logic
Keywords :
backpropagation; neural chips; neural net architecture; pattern recognition; random-access storage; RAM structure; backpropagation; intelligent memory; learning mode; neural architectures; neural networks; pattern recognition; Artificial intelligence; Artificial neural networks; Computer architecture; Intelligent networks; Logic arrays; Machine intelligence; Parallel processing; Pattern recognition; Random access memory; Reconfigurable logic;
Journal_Title :
Micro, IEEE
DOI :
10.1109/MM.2002.1013302
